{"id":"W3082498369","doi":"10.1109/tpami.2020.3020800","title":"GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Artificial intelligence; Normal; Depth map; Metric (unit); Computer vision; Pixel; Surface (topology); Consistency (knowledge bases); Enhanced Data Rates for GSM Evolution; Artificial neural network; Boundary (topology); Algorithm; Mathematics; Image (mathematics); Geometry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004345437,0.001922595,0.000907468,0.0008292648,0.0002749911,0.0007303471,0.003248912,0.001142436,0.003064984],"category_scores_gemma":[0.001475763,0.0006838262,0.0007613294,0.000909857,0.0004369715,0.001665692,0.001369647,0.001365473,0.001609141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000882022,"about_ca_system_score_gemma":0.0009973809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01465173,"about_ca_topic_score_gemma":0.02803346,"domain_scores_codex":[0.9996911,0.00002891531,0.00001229732,0.000114486,0.000113639,0.00003957157],"domain_scores_gemma":[0.9997143,0.00005911586,0.0000334455,0.00006492855,0.0001097852,0.00001831775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001861254,0.0001314472,0.002226504,0.0001260507,0.000146794,0.0001204326,0.00004765432,0.4730865,0.01221227,0.004244733,0.01577623,0.4916953],"study_design_scores_gemma":[0.000008750822,0.00002233689,0.0001877106,0.000004652843,0.000009462219,0.00002767813,0.000005021246,0.9948989,0.002172219,0.00132677,0.001329255,0.000007235616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0231611,0.000800532,0.9584145,0.0002709393,0.0001644421,0.0001089315,0.0008799321,0.01327765,0.002921984],"genre_scores_gemma":[0.3108947,0.0006876491,0.6719323,0.0006241071,0.0001088692,0.0002729477,0.005411174,0.001005475,0.009062741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01465173,"threshold_uncertainty_score":0.02913284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02983077716167372,"score_gpt":0.2780307465243003,"score_spread":0.2481999693626265,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}